Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Putt Wil kin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ratings
    0.44
    carbon
    0.44
     शुक्
    0.43
    actor
    0.42
    рати
    0.41
    Carbon
    0.40
    деш
    0.40
    ph
    0.40
    states
    0.40
     phosphates
    0.40
    POSITIVE LOGITS
    وند
    0.47
     Kier
    0.46
     Madd
    0.44
     Cag
    0.42
     Ayo
    0.42
     Bou
    0.42
     bou
    0.41
    Ṛ
    0.41
     Nd
    0.41
     induc
    0.39
    Act Density 0.003%

    No Known Activations